Become A Wiser, More Profitable Investor

Towards Robust Pruning: An Adaptive Knowledge-Retention Pruning Strategy for Language Models. (arXiv:2310.13191v1 [cs.CL])

science

The pruning objective has recently extended beyond accuracy and sparsity to robustness in language models. Despite this, existing methods struggle to enhance robustness against adversarial attacks when continually increasing model sparsity and require a retraining process. As humans step into the era of large language models, these issues become increasingly prominent. This paper proposes that the robustness of language models is proportional to the extent of pre-trained knowledge they encompass. Accordingly, we introduce a post-training pruning strategy designed to faithfully replicate the embedding space and feature space of dense language models, aiming to conserve more pre-trained knowledge during the pruning process.

arXiv     Oct 23, 2023